Upload folder using huggingface_hub

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e8bc85aa083b75a30b7ba295a754ce02e0c5fadb33d7e0468f13c629931a720
+oid sha256:447a1e485a3f111cf2ef769f24073ec0e50b4a06884a6f49f4dab1d2a562b562
 size 160086542

all_results.json

@@ -1,17 +1,17 @@
 {
     "epoch": 0.99,
-    "eval_accuracy": 0.82,
-    "eval_f1_score": 0.8184577723378215,
-    "eval_gmean": 0.8139876199369547,
-    "eval_loss": 0.33375000953674316,
-    "eval_precision": 0.8230000000000001,
-    "eval_recall": 0.82,
-    "eval_runtime": 163.2928,
-    "eval_samples_per_second": 0.306,
-    "eval_steps_per_second": 0.043,
+    "eval_accuracy": 0.9,
+    "eval_f1_score": 0.9015245623941276,
+    "eval_gmean": 0.8701338213935068,
+    "eval_loss": 0.30312439799308777,
+    "eval_precision": 0.9039473684210526,
+    "eval_recall": 0.9,
+    "eval_runtime": 152.4589,
+    "eval_samples_per_second": 0.328,
+    "eval_steps_per_second": 0.046,
     "total_flos": 1.1914693337677824e+17,
-    "train_loss": 0.34641749884492606,
-    "train_runtime": 20162.3344,
-    "train_samples_per_second": 0.298,
+    "train_loss": 0.3471187468497984,
+    "train_runtime": 19325.8318,
+    "train_samples_per_second": 0.31,
     "train_steps_per_second": 0.005
 }

eval_results.json

@@ -1,12 +1,12 @@
 {
     "epoch": 0.99,
-    "eval_accuracy": 0.82,
-    "eval_f1_score": 0.8184577723378215,
-    "eval_gmean": 0.8139876199369547,
-    "eval_loss": 0.33375000953674316,
-    "eval_precision": 0.8230000000000001,
-    "eval_recall": 0.82,
-    "eval_runtime": 163.2928,
-    "eval_samples_per_second": 0.306,
-    "eval_steps_per_second": 0.043
+    "eval_accuracy": 0.9,
+    "eval_f1_score": 0.9015245623941276,
+    "eval_gmean": 0.8701338213935068,
+    "eval_loss": 0.30312439799308777,
+    "eval_precision": 0.9039473684210526,
+    "eval_recall": 0.9,
+    "eval_runtime": 152.4589,
+    "eval_samples_per_second": 0.328,
+    "eval_steps_per_second": 0.046
 }

runs/Apr01_01-51-32_8c1b24df09a3/events.out.tfevents.1711936295.8c1b24df09a3.34.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c572fd7ce27abd06daa26dd3caf7cb2f6eb5656979b4fa7d8c94f6586d3c442c
+size 9095

runs/Apr01_01-51-32_8c1b24df09a3/events.out.tfevents.1711955773.8c1b24df09a3.34.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4860f8be118fc6bcdcbd210a120fed1e42aa6673bbed555f8ffbcb20ca03f23f
+size 605

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 0.99,
     "total_flos": 1.1914693337677824e+17,
-    "train_loss": 0.34641749884492606,
-    "train_runtime": 20162.3344,
-    "train_samples_per_second": 0.298,
+    "train_loss": 0.3471187468497984,
+    "train_runtime": 19325.8318,
+    "train_samples_per_second": 0.31,
     "train_steps_per_second": 0.005
 }

trainer_state.json

@@ -10,127 +10,127 @@
   "log_history": [
     {
       "epoch": 0.09,
-      "grad_norm": 6.78125,
+      "grad_norm": 7.34375,
       "learning_rate": 1.8681318681318682e-05,
-      "loss": 0.3728,
+      "loss": 0.3872,
       "step": 8
     },
     {
       "epoch": 0.17,
-      "grad_norm": 5.03125,
+      "grad_norm": 5.59375,
       "learning_rate": 1.6923076923076924e-05,
-      "loss": 0.353,
+      "loss": 0.3649,
       "step": 16
     },
     {
       "epoch": 0.26,
-      "grad_norm": 6.5,
+      "grad_norm": 5.9375,
       "learning_rate": 1.5164835164835166e-05,
-      "loss": 0.3137,
+      "loss": 0.4135,
       "step": 24
     },
     {
       "epoch": 0.3,
-      "eval_accuracy": 0.82,
-      "eval_f1_score": 0.8184577723378215,
-      "eval_gmean": 0.8139876199369547,
-      "eval_loss": 0.33320313692092896,
-      "eval_precision": 0.8230000000000001,
-      "eval_recall": 0.82,
-      "eval_runtime": 163.4252,
-      "eval_samples_per_second": 0.306,
-      "eval_steps_per_second": 0.043,
+      "eval_accuracy": 0.9,
+      "eval_f1_score": 0.9015245623941276,
+      "eval_gmean": 0.8701338213935068,
+      "eval_loss": 0.3042968809604645,
+      "eval_precision": 0.9039473684210526,
+      "eval_recall": 0.9,
+      "eval_runtime": 150.7919,
+      "eval_samples_per_second": 0.332,
+      "eval_steps_per_second": 0.046,
       "step": 28
     },
     {
       "epoch": 0.34,
-      "grad_norm": 7.40625,
+      "grad_norm": 9.0,
       "learning_rate": 1.3406593406593406e-05,
-      "loss": 0.3488,
+      "loss": 0.3769,
       "step": 32
     },
     {
       "epoch": 0.43,
-      "grad_norm": 4.375,
+      "grad_norm": 5.71875,
       "learning_rate": 1.164835164835165e-05,
-      "loss": 0.3013,
+      "loss": 0.3004,
       "step": 40
     },
     {
       "epoch": 0.51,
-      "grad_norm": 8.375,
+      "grad_norm": 6.5625,
       "learning_rate": 9.890109890109892e-06,
-      "loss": 0.4057,
+      "loss": 0.3444,
       "step": 48
     },
     {
       "epoch": 0.6,
-      "grad_norm": 5.90625,
+      "grad_norm": 7.6875,
       "learning_rate": 8.131868131868132e-06,
-      "loss": 0.3598,
+      "loss": 0.3599,
       "step": 56
     },
     {
       "epoch": 0.6,
-      "eval_accuracy": 0.82,
-      "eval_f1_score": 0.8184577723378215,
-      "eval_gmean": 0.8139876199369547,
-      "eval_loss": 0.3338281214237213,
-      "eval_precision": 0.8230000000000001,
-      "eval_recall": 0.82,
-      "eval_runtime": 163.4717,
-      "eval_samples_per_second": 0.306,
-      "eval_steps_per_second": 0.043,
+      "eval_accuracy": 0.9,
+      "eval_f1_score": 0.9015245623941276,
+      "eval_gmean": 0.8701338213935068,
+      "eval_loss": 0.3040618896484375,
+      "eval_precision": 0.9039473684210526,
+      "eval_recall": 0.9,
+      "eval_runtime": 150.6764,
+      "eval_samples_per_second": 0.332,
+      "eval_steps_per_second": 0.046,
       "step": 56
     },
     {
       "epoch": 0.68,
-      "grad_norm": 7.6875,
+      "grad_norm": 5.78125,
       "learning_rate": 6.373626373626373e-06,
-      "loss": 0.295,
+      "loss": 0.3341,
       "step": 64
     },
     {
       "epoch": 0.77,
-      "grad_norm": 6.8125,
+      "grad_norm": 6.3125,
       "learning_rate": 4.615384615384616e-06,
-      "loss": 0.3881,
+      "loss": 0.3116,
       "step": 72
     },
     {
       "epoch": 0.85,
-      "grad_norm": 5.90625,
+      "grad_norm": 5.53125,
       "learning_rate": 2.8571428571428573e-06,
-      "loss": 0.3761,
+      "loss": 0.3222,
       "step": 80
     },
     {
       "epoch": 0.9,
-      "eval_accuracy": 0.82,
-      "eval_f1_score": 0.8184577723378215,
-      "eval_gmean": 0.8139876199369547,
-      "eval_loss": 0.33375000953674316,
-      "eval_precision": 0.8230000000000001,
-      "eval_recall": 0.82,
-      "eval_runtime": 163.4454,
-      "eval_samples_per_second": 0.306,
-      "eval_steps_per_second": 0.043,
+      "eval_accuracy": 0.9,
+      "eval_f1_score": 0.9015245623941276,
+      "eval_gmean": 0.8701338213935068,
+      "eval_loss": 0.30312439799308777,
+      "eval_precision": 0.9039473684210526,
+      "eval_recall": 0.9,
+      "eval_runtime": 152.7595,
+      "eval_samples_per_second": 0.327,
+      "eval_steps_per_second": 0.046,
       "step": 84
     },
     {
       "epoch": 0.94,
-      "grad_norm": 4.96875,
+      "grad_norm": 7.84375,
       "learning_rate": 1.098901098901099e-06,
-      "loss": 0.2953,
+      "loss": 0.3446,
       "step": 88
     },
     {
       "epoch": 0.99,
       "step": 93,
       "total_flos": 1.1914693337677824e+17,
-      "train_loss": 0.34641749884492606,
-      "train_runtime": 20162.3344,
-      "train_samples_per_second": 0.298,
+      "train_loss": 0.3471187468497984,
+      "train_runtime": 19325.8318,
+      "train_samples_per_second": 0.31,
       "train_steps_per_second": 0.005
     }
   ],